k-awtycarroll
commited on
Commit
•
b021aa5
1
Parent(s):
5bd89ad
my-great-gpt2-review-model-katie
Browse files
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
-
base_model: distilgpt2
|
3 |
license: apache-2.0
|
|
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
@@ -13,14 +13,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# my-great-gpt2-review-model-katie
|
15 |
|
16 |
-
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
-
|
19 |
-
-
|
20 |
-
- eval_runtime: 0.643
|
21 |
-
- eval_samples_per_second: 155.525
|
22 |
-
- eval_steps_per_second: 20.218
|
23 |
-
- step: 0
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -47,9 +43,16 @@ The following hyperparameters were used during training:
|
|
47 |
- lr_scheduler_type: linear
|
48 |
- num_epochs: 0.3
|
49 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
50 |
### Framework versions
|
51 |
|
52 |
- Transformers 4.44.0
|
53 |
- Pytorch 2.3.1+cu121
|
54 |
-
- Datasets 2.
|
55 |
- Tokenizers 0.19.1
|
|
|
1 |
---
|
|
|
2 |
license: apache-2.0
|
3 |
+
base_model: distilgpt2
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
|
|
13 |
|
14 |
# my-great-gpt2-review-model-katie
|
15 |
|
16 |
+
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 3.8380
|
19 |
+
- Model Preparation Time: 0.0014
|
|
|
|
|
|
|
|
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
43 |
- lr_scheduler_type: linear
|
44 |
- num_epochs: 0.3
|
45 |
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time |
|
49 |
+
|:-------------:|:------:|:----:|:---------------:|:----------------------:|
|
50 |
+
| 3.9332 | 0.3001 | 3045 | 3.8380 | 0.0014 |
|
51 |
+
|
52 |
+
|
53 |
### Framework versions
|
54 |
|
55 |
- Transformers 4.44.0
|
56 |
- Pytorch 2.3.1+cu121
|
57 |
+
- Datasets 2.21.0
|
58 |
- Tokenizers 0.19.1
|
config.json
CHANGED
@@ -7,6 +7,7 @@
|
|
7 |
],
|
8 |
"attn_pdrop": 0.1,
|
9 |
"bos_token_id": 50256,
|
|
|
10 |
"embd_pdrop": 0.1,
|
11 |
"eos_token_id": 50256,
|
12 |
"id2label": {
|
@@ -17,6 +18,7 @@
|
|
17 |
"LABEL_0": 0
|
18 |
},
|
19 |
"layer_norm_epsilon": 1e-05,
|
|
|
20 |
"model_type": "gpt2",
|
21 |
"n_ctx": 1024,
|
22 |
"n_embd": 768,
|
|
|
7 |
],
|
8 |
"attn_pdrop": 0.1,
|
9 |
"bos_token_id": 50256,
|
10 |
+
"do_sample": true,
|
11 |
"embd_pdrop": 0.1,
|
12 |
"eos_token_id": 50256,
|
13 |
"id2label": {
|
|
|
18 |
"LABEL_0": 0
|
19 |
},
|
20 |
"layer_norm_epsilon": 1e-05,
|
21 |
+
"max_length": 50,
|
22 |
"model_type": "gpt2",
|
23 |
"n_ctx": 1024,
|
24 |
"n_embd": 768,
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 327657928
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd84a55c642eafd178eceb47d09a5319212fa86efb8fac9d39da924848ff0171
|
3 |
size 327657928
|
runs/Aug15_03-47-55_4f4ba484ebe4/events.out.tfevents.1723693686.4f4ba484ebe4.3860.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60a924732b3cf560235faa09358a5d79e6c8d92ab95d6ed07712118cdb48d0e5
|
3 |
+
size 7523
|
runs/Aug15_03-47-55_4f4ba484ebe4/events.out.tfevents.1723694281.4f4ba484ebe4.3860.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6cc5934a2ab94062c916f04d33b03fdd4eca5f7db592e24fc60785c9a2a333ad
|
3 |
+
size 425
|